The BNA™ Platform is to be used by qualified medical professionals for the post-hoc statistical analysis of the human electroencephalogram ("EEG"), including event-related potentials ("ERPs').

This device is indicated for use in individuals 12 to 85 years of age.

The BNA™ Platform is to be used with the Auditory Oddball, Visual Go No-Go (age range of 25 to 85 years), and Eyes-Closed tasks.

Device Description

The BNATM Platform is intended for the post-hoc statistical analysis of the human electroencephalogram ("EEG"), utilizing both resting-state EEG and Event-Related Potentials ("ERP") in a patient's response to outside stimuli during various states of alertness, disease, diagnostic testing, treatment, surgery, or drug related dysfunction. An Event-Related Potential (or "evoked response") is an electrical potential recorded from the nervous system following the presentation of a stimulus (e.g., as part of a cognitive task). An ERP signal consists of typical ERP components - positive or negative voltage spatiotemporal peaks within the ERP waveform that are measured within one second post-stimulus presentation. The BNATM Platform is intended to analyze EEG data recorded at rest and during the performance of two conventionally used ERP tasks, the Auditory Oddball (AOB) and the Visual Go No-Go (VGNG).

The EEG is recorded continuously while the patient is at rest with eyes-closed (hereby Eyes-Closed) or performs one of the ERP tasks (hereby ERP tasks). The acquisition site is asked to provide reliable samples of artifact-free digital EEG for purposes of analysis. After the recording, the artifact-free EEG data is imported into the BNATM Platform and is automatically analyzed by the algorithm and the results of the processed data are compiled into individualized Reports:

. ERP Report
Behavioral Report ●
. Summary Report
Resting-State EEG Report ●

Scores are presented as Z-Scores based on comparing the patient to an age-matched relevant reference group based on elminda's normative database. This presentation expresses the differences between the patient and the reference group.

The BNA™ Reports are intended to be used by clinicians to enable the evaluation of the patient's brain activity during a specific task compared to an age-range matched reference group.

The system consists of the following components: a computer environment; EEG data input software algorithms for BNA™ calculations; a report generator and a functionality for data transfer and storage.

The device processes and analyzes data received from a dedicated, commercially available, and FDA cleared EEG system, which complies with the BNATM Platform specifications.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

Performance Metric	Acceptance Criteria (Success Rate)	Reported Device Performance	Discussion
Normality of EEG Scores	Pass at least 2 of 4 normality tests (p-value > 0.05)	All Resting-EEG and ERP scores pass "two out of four" method tests with a success rate > 97% for Resting-EEG and > 98% for ERP.	The study aimed to demonstrate that the expanded age ranges and tasks maintain the statistical properties of the original predicate device. A success rate above 97% and 98% for ERP scores indicates high compliance with the normal distribution assumption, allowing for reliable Z-score interpretation. This is explicitly stated to be "in accordance with the success rates presented in the predicate device statistical performance and, from a clinical perspective, allow for an accurate clinical interpretation of z-scores."
Gaussian Leave-One-Out Sensitivity Test (for Resting-EEG)	Success rate > 97.5%	Resting-EEG scores pass with a success rate > 97.5%.	This additional test for Resting-EEG further validates the robustness of the normality assumption, with the reported success rate meeting the criterion. The document notes this is an "acceptable percentage of failures, given the large number of scores tested."
Poolability of Reference Group Data	Significant age-effect (p < 0.05) following FDR correction	All AOB and VGNG ERP scores pass the poolability test with a success rate of 99% and 100%, respectively.	Poolability refers to the ability to combine data from different sources (or age groups in this case) into a single reference group without significant bias from age. High success rates (99% and 100%) indicate that the data can be reliably grouped by age, which is crucial for creating the age-matched reference database. This is described as an "acceptable percentage of failures, given the large amount of scores tested, allowing for a reliable division of the entire dataset into age groups."
Test-Retest Reliability	N/A (Statistical Estimates Provided)	Bland-Altman analysis provides test-retest reliability statistical estimates for all combinations of tasks, conditions, and parameters.	While no specific numerical acceptance criterion is provided for test-retest reliability, the study demonstrates that these estimates can be used by clinicians to estimate changes in BNA™ Scores between successive visits. This implies that the reliability is sufficient for its clinical purpose, though the exact threshold for "sufficient" isn't explicitly stated in the provided text.

Study Details

Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Healthy volunteers aged 12-85 years old were recruited. The reference group for AOB tasks includes subjects from 12-85 years across nine age groups. The reference group for VGNG tasks includes subjects from 25-85 years across five age groups. The Resting-EEG reference groups were created with 133 overlapping bins covering the 12-85 age range.
- Specific numbers of subjects in the test sets (distinct from the normative database mentioned below) for normality and poolability tests are not explicitly stated, but the discussion implies these tests were performed on the Reference-Group Database itself.
- Data Provenance: Retrospective and prospective. Healthy volunteers were recruited from 13 clinical sites, with 12 sites located within the US. Some volunteers participated at a single visit, while others participated in two successive visits (approximately 1 week apart) for the re-test database, indicating prospective data collection for reliability analysis. The "Reference-Group Database" is inherently a collection of retrospective or prospectively collected data used for comparison.
Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:
- The document does not explicitly state the number or qualifications of experts used to establish ground truth for the test set in the context of diagnostic accuracy.
- The study focuses on validating the statistical properties of the normative database (normality, poolability, test-retest reliability). The "ground truth" in this context is the statistical distribution of EEG/ERP scores in a healthy population.
Adjudication Method for the Test Set:
- Not applicable in the traditional sense. The study's focus is on the statistical validation of a normative database rather than diagnostic accuracy against a clinical ground truth requiring adjudication. The "ground truth" is derived from statistical analysis of the healthy volunteer data itself.
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study was done. The study focuses on the validation of the device's statistical analysis and normative database, not on comparing human reader performance with and without AI assistance.
Standalone Performance (Algorithm Only) Study:
- A standalone performance study was conducted in the sense that the algorithm's outputs (EEG/ERP scores, Z-scores based on the normative database) were directly evaluated for their statistical properties (normality, poolability, test-retest reliability). This is an "algorithm only" evaluation as it validates the outputs of the BNA™ Platform itself.
Type of Ground Truth Used:
- The ground truth used is based on statistical properties of neurophysiological data from a large cohort of healthy individuals. Specifically, it involves:
  - Normality: Confirmation that EEG/ERP scores conform to a normal distribution within their respective age groups.
  - Poolability: Validation that data across different sites or age segments can be combined appropriately for the normative database.
  - Test-retest reliability: Measurement of the consistency of the device's output over repeated measurements in healthy individuals.
- This is not a traditional "clinical ground truth" like pathology or outcomes data that would be used to assess diagnostic accuracy against a disease state. Instead, it validates the reference data that the device uses for comparison.
Sample Size for the Training Set:
- The document refers to a "Reference-Group Database" that serves a similar purpose to a training set for creating the normative data against which patient scores are compared.
- AOB Tasks: 1900 subjects covering age range 12-85 years.
- Eyes-Closed Resting-State EEG: 1407 subjects covering age range 12-85 years.
- VGNG Tasks: 1005 subjects covering age range 25-85 years.
How the Ground Truth for the Training Set was Established:
- The "ground truth" (the normative database) for the training set was established through the collection of electrophysiological activity (EEG/ERPs) from a large cohort of healthy volunteers aged 12-85.
- These volunteers performed specific tasks: Eyes-Closed (EC), Auditory Oddball (AOB), and Visual Go-No-Go (VGNG).
- The collected data was then compiled to create reference groups, divided into specific age bins for each task. The process of establishing this "ground truth" involved ensuring the statistical validity of the collected data, including the normality testing and poolability analysis as detailed in the acceptance criteria. The BNA™ Platform then compares a patient's data to this established normative database.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

elminda, Ltd % Donna-Bea Tillman Senior Consultant Biologics Consulting 1555 King Street. Suite 300 Alexandria, Virginia 22314

Re: K202588

Trade/Device Name: BNA Platform Regulation Number: 21 CFR 882.1400 Regulation Name: Electroencephalograph Regulatory Class: Class II Product Code: OLU Dated: September 4, 2020 Received: September 8, 2020

Dear Donna-Bea Tillman:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's

{1}------------------------------------------------

requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Jay Gupta Assistant Director DHT5A: Division of Neurosurgical, Neurointerventional and Neurodiagnostic Devices OHT5: Office of Neurological and Physical Medicine Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K202588

Device Name BNA™ Platform

Indications for Use (Describe)

The BNA™ Platform is to be used by qualified medical professionals for the post-hoc statistical analysis of the human electroencephalogram ("EEG"), including event-related potentials ("ERPs').

This device is indicated for use in individuals 12 to 85 years of age.

The BNA™ Platform is to be used with the Auditory Oddball, Visual Go No-Go (age range of 25 to 85 years), and Eyes-Closed tasks.

Type of Use (Select one or both, as applicable)

☑ Prescription Use (Part 21 CFR 801 Subpart D)	☐ Over-The-Counter Use (21 CFR 801 Subpart C)
---------------------------------------------------------------------------------------------------------------------	--------------------------------------------------------------------------------------------------------------------

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

In accordance with 21 CFR 807.87(h) and (21 CFR 807.92) the 510(k) Summary for the BNA™ Platform is provided below.

1. SUBMITTER

Applicant:	elminda Ltd.
	1 Arie Shenkar Street
	Herzliya, 4672501, Israel
Contact:	Keren Elghouzzi-Kazachinsky
	QA/RA Manager
	Elminda
	+972-53 7739780
	quality@elminda.com
Submission Correspondent:	Donna-Bea Tillman, Ph.D.
	Senior Consultant
	Biologics Consulting
	1555 King St, Suite 300
	Alexandria, VA 22314
	410-531-6542
	dtillman@biologicsconsulting.com
Date Prepared:	December 3, 2020

2. DEVICE

Device Trade Name:	BNA™ Platform
Device Common Name:	Normalizing Quantitative ElectroencephalographSoftware
Classification Name:	21 CFR 882.1400 Electroencephalograph,
Regulatory Class:	II
Product Code:	OLU

PREDICATE DEVICE 3.

Predicate Device:	K121119 - BNA™ Analysis System (Elminda)
Secondary Predicate Device:	K171414 - qEEG-Pro (BrainMasters Technologies, Inc)

{4}------------------------------------------------

DEVICE DESCRIPTION 4.

. ERP Report
Behavioral Report ●
. Summary Report
Resting-State EEG Report ●

The BNA™ Reports are intended to be used by clinicians to enable the evaluation of the patient's brain activity during a specific task compared to an age-range matched reference group.

The device processes and analyzes data received from a dedicated, commercially available, and FDA cleared EEG system, which complies with the BNATM Platform specifications.

5. INTENDED USE/INDICATIONS FOR USE

The BNA™ Platform is to be used by qualified medical professionals for the post-hoc statistical analysis of the human electroencephalogram ("EEG"), including event-related potentials ("ERPs").

This device is indicated for use in individuals 12 to 85 years of age.

{5}------------------------------------------------

The BNA™ Platform is to be used with the Auditory Oddball, Visual Go No-Go (age range of 25 to 85 years), and Eyes-Closed tasks.

6. SUBSTANTIAL EQUIVALENCE

Comparison of Indications

The subject device and the two predicate devices all have the same intended use, namely, to provide analyses of human EEG data. The features of the subject device have been expanded from those of the primary predicate BNA device to include additional age ranges and tasks, similar to the capabilities of the predicate qEEG-Pro device. The differences in the wording of the Indications for use reflect this expansion in features as well as a minor modification to reflect a change to the currently accepted terminology of "event-related potentials" as opposed to "evoked response potentials". These differences do not impact the intended use, and therefore the subject device has the same intended use as the predicate device.

Technological Comparisons

The table below compares the key technological feature of the subject devices to the predicate device K121119 - BNATM Analysis System (K121119) and qEEG-Pro (K171414).

	BNA™ Platform	BNA™ AnalysisSystem	qEEG-Pro	Discussion
	Subject Device	Primary PredicateDevice	Secondary PredicateDevice
Manufacturer	elminda	elminda	BrainMastersTechnologies, Inc	N/A
510k Number	N/A	K121119	K171414	N/A
Product Code	OLU	OLU	OLU	Same as Predicate
Intendedpatientpopulation	12-85 years (for AOBand Eyes closed tasks)25-85 years (for VGNG)	14-24 years	4-82 years	Extended age range;Clinical datademonstrates equivalentperformance.
Tasks	AOB, VGNG, and Eyes-Closed Resting-State	Auditory Oddball(AOB)	Eyes-Closed andEyes-Open Resting-State	Additional Tasks:VGNG andResting-State EEG;clinical testingdemonstrates equivalentin safety andeffectiveness.
Intended User	Used by a Clinician /Prescription device	Used by a Clinician /Prescription device	Used by a Clinician/ Prescription device	Same as predicate
	BNA™ Platform	BNA™ AnalysisSystem	qEEG-Pro	Discussion
	Subject Device	Primary PredicateDevice	Secondary PredicateDevice
Band Passing(ERP)	Frequencydecomposition of theEEG data into: Delta,Theta and Alphafrequency bands.	Frequencydecomposition of theEEG data into: Delta,Theta and Alphafrequency bands	Not relevant - doesnot cover ERPfunctions	Same as Predicate
Time-Analysis(ERP)	A time domain peakanalysis is performed	A time domain peakanalysis is performed	Not relevant (ERPonly)	Same as predicate
Analysis ofBand-passed(ERP)	Peak analysis is appliedfor the individual band-passed time-series (i.e.,peak analysis for Alpha,Delta, Theta)	Peak analysis is appliedfor the individual band-passed time-series (i.e.,peak analysis for Alpha,Delta, Theta)	Not relevant (ERPonly)	Same as Predicate
PeakAnalysis(ERP)	Peak-detection at thelevel of the decomposedERP (post frequencydecomposition) isperformed for eachelectrode separatelyfollowed by selection ofthe highest peak.	Peak-detection at thelevel of thedecomposed ERP(post frequencydecomposition) isperformed for eachelectrode separately in aspecific time and spacerange	Not relevant (ERPonly)	Performance testingdemonstrates correctimplementation. Theresults of poolabilityand normalityperformance validationtest demonstratedequivalence to thesuccess rate ofpredicate and do notraise new issue ofsafety and effectiveness
Neural-Consistency	The algorithm calculatesa new score – 'NeuralConsistency' based onthe similarity of theamplitude activationbetween single-ERPtrials	No; new score	Not relevant (ERPonly)	Performance testingdemonstrates correctimplementation. Theresults of poolabilityand normalityperformance validationtest demonstratedequivalence to thesuccess rate ofpredicate and do notraise new issue ofsafety and effectiveness
ReportedERP peaks	The highest ERP peakswithin literature-basedtime constraints, whichshow the highest spatio-temporal similarity to the	The ERP peaks atnetwork-based, pre-defined electrodesappear in the report	Not relevant (ERPonly)	Performance testingdemonstrates correctimplementation. Theresults of poolabilityand normalityperformance validationtest demonstratedequivalence to thesuccess rate of
	BNATM Platform	BNATM AnalysisSystem	qEEG-Pro	Discussion
	Subject Device	Primary PredicateDevice	Secondary PredicateDevice
	group ERP appear in thereport			equivalence to thesuccess rate ofpredicate and do notraise new issue ofsafety and effectiveness
NetworkAnalysis	No network analysis	Network analysis basedon the ERP-peaks asthe network nodes	Not relevant (ERPonly)	Feature removed
Topographical maps ofERP	Subject ERP-peakposition is displayed on atopographical maptogether with the groupERP-peak position.	Z-scores are presentedas topographical-maps(electrode coordinates).Networks activity overtime is presented intime evolution maps	Not relevant (ERPonly)	Performance testingdemonstrates correctimplementation. Theresults of poolabilityand normalityperformance validationtest demonstratedequivalence to thesuccess rate ofpredicate and do notraise new issue ofsafety and effectiveness
ERPWaveforms	Broadband (0.5-30Hz)and band-pass (Delta,Theta and Alpha) ERPwaveforms of the subjectare visualized incomparison to theaveraged ERP waveformof the age-matchedreference group.	Broadband (0.5-30Hz)ERP waveforms of thesubject are visualized incomparison to theaveraged ERPwaveform of the age-matched referencegroup.	Not relevant (ERPonly)	Performance testingdemonstrates correctimplementation. Theresults of poolabilityand normalityperformance validationtest demonstratedequivalence to thesuccess rate ofpredicate and do notraise new issue ofsafety and effectiveness
ERPwaveformsdisplay bystimulus type	The ERP waveformdisplay is divided intosections by stimulus type	The ERP waveformdisplay is divided intosections by stimulustype	Not relevant (ERPonly)	Same as Predicate
Display ofrepresentativeERPs	Within each stimulus-section, 19 panelsrepresent 19 selectedelectrode locations onthe scalp. These areelectrode positionsdescribed in theinternational 10-20	Within each stimulus-section 20 panelsrepresent 20 selectedelectrode locations onthe scalp. These areelectrode positionsdescribed in theinternational 10-20	Not relevant (ERPonly)	Performance testingdemonstrates correctimplementation.
	BNA™ Platform	BNA™ Analysis System	qEEG-Pro	Discussion
	Subject Device	Primary Predicate Device	Secondary Predicate Device
	system of electrode placement.	system of electrode placement.
Comparison to Normative Database	Yes; 1900 and 1407 subjects covering the age-range 12-85 for the tasks AOB and Eyes-Closed Resting-State EEG, respectively. In addition, 1005 subjects covering the age-range 25-85 for the VGNG task	Yes; 120 subjects in the age-range 14-24 AOB task only	Yes: Z-scores are calculated based on reference-group mean and std. (Not for ERP)	Reference database expanded to include additional subjects; performance testing demonstrates validity of revised database
Resting-State EEG data Comparison against the Normative Database	Yes; 1407 subjects covering the age-range 12-85 for Eyes-Closed Resting-state EEG	No	Yes; 1482 samples (eyes-closed); 1231 subjects (eyes-open)	Clinical data demonstrates equivalent performance
Resting-State EEG Spectral-Analysis	Yes; 4 frequency bands (delta, theta, alpha, and beta)	No	Yes; 4 frequency bands (delta, theta, alpha, and beta)	Same as predicate
Spectral Analysis scores	Yes, the following scores are extracted from PSD: Average Absolute Power, Relative Power, Individual Alpha Frequency, Hemispheric Asymmetry and Frequency Ratios	No	Yes; The following scores are extracted from PSD: Absolute Power, Relative Power, Alpha Peak Frequency, Hemispheric Asymmetry, Coherence and Frequency Ratios	The Average Absolute Power score is well-known in the scientific literature and was statistically validated for normality.
Age Range Included in the Normative Database	12-85 years	14-24 years	4-82 years	The existing normative database has been extended to include additional age-ranges. The additional age-bins and tasks were clinically validated.
	BNA™ Platform	BNA™ AnalysisSystem	qEEG-Pro	Discussion
	Subject Device	Primary PredicateDevice	Secondary PredicateDevice
VisualDisplay ofEEG	Yes: topographical maps of Average Absolute and Relative Power, Individual Alpha Frequency, Hemispheric Asymmetry and Frequency Ratios	No	Yes: topographical maps of Absolute and Relative Power, Power Asymmetry, and Coherence for 19 monopolar and 171 selected bipolar derivations of the EEG	The features are equivalent and the results of performance testing demonstrate equivalent performance
Hardware	Runs on the AWS cloud and accepts EEG data from all sites	Standalone computer running the BNA™ engine locally and contains the EEG/ERP data locally		The results of System and Software Test Verification demonstrate that the subject device meets the defined requirements

Table 1: Technological Comparison

{6}------------------------------------------------

{7}------------------------------------------------

{8}------------------------------------------------

{9}------------------------------------------------

In conclusion, the differences in technological characteristics do not raise new questions of safety and effectiveness and the BNA™ Platform can be found substantially equivalent to the predicate devices.

7. PERFORMANCE DATA

Biocompatibility Testing

BNA™ Platform is a software only device. There are no direct or indirect patient-contacting components of the subject device. Therefore, patient contact information is not needed for this device.

Sterilization and Shelf Life

BNA™ Platform is a software only device. Therefore, sterilization and shelf life are not applicable.

Electrical safety and electromagnetic compatibility (EMC)

Not applicable. BNA™ Platform is a software only device. The device contains no electric components, generates no electrical emissions, and uses no electrical energy of any type.

Software Verification and Validation Testing

Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." The software for this

{10}------------------------------------------------

device was considered as a moderate level of concern. Testing was conducted to ensure the product works as designed and to validate the performance of the device.

Bench Testing

Not applicable. Bench testing was not necessary to establish the substantial equivalence of this device.

Animal Testing

Not applicable. Animal studies were not necessary to establish the substantial equivalence of this device.

Clinical Data

The objective of the clinical study was to establish and validate the Reference-Group Database and to evaluate its test-retest reliability.

Healthy volunteers aged 12-85 years old were recruited from 13 clinical sites, with 12 sites located within the US. Depending on the site's protocol, the volunteers either participated at a single visit, or at two successive visits, separated by approximately 1 week to provide data for the re-test database. Brain electrophysiological activity was collected using the BNA 100 Platform while the participants performed the Eyes-Closed (EC) task and one or more cognitive task, including the Auditory Oddball (AOB) task (using the hearing adjusted version for participants older than 50 years) and the Visual Go-No-Go (VGNG) task.

The Reference-Group Database for the AOB and VGNG tasks is divided into the following age groups: 25-35, 35-50, 50-65, 65-75, and 75-85 years for VGNG, and 12-14, 14-16, 16-18, 18-25, 25-35, 35-50, 50-65, 65-75, and 75-85 years for AOB. For the Resting-EEG, reference groups were created at 0.5-year resolution by taking 133 overlapping bins covering the range 12-85.

EEG/ERP scores were transformed and validated for their normal distribution by using the same methodology in accordance with the predicate device: using four normality tests Anderson-Darling, the Cramer-von Mises, the Kolmogorov-Smirnov, and the Shapiro-Wilk tests. A score was considered to be normally distributed if at least 2 of the four tests were not statistically significant (p-value > 0.05) Normality of the EEG Scores was also tested using a Gaussian leaveone-out sensitivity test.

The normality test results are in accordance with the success rates presented in the predicate device statistical performance and, from a clinical perspective, allow for an accurate clinical interpretation of z-scores.

All Resting-EEG and ERP scores pass the 'two out of four' method tests (i.e., passing at least 2 out of 4 different normality tests) with a success rate above 97% and 98%, respectively, with Resting-EEG scores also passing the Gaussian leave-one-out sensitivity tests with a success rate larger than 97.5% an acceptable percentage of failures, given the large number of scores tested. These results are in accordance with the success rates presented in the predicate device statistical performance and allow for an accurate clinical interpretation of z-scores.

Poolability of the Reference Group data was tested with a linear regression model for each combination of ERP score or behavioral performance score and age-bin and checked for cases

{11}------------------------------------------------

with a significant age-effect (p<0.05) following False Discovery Rate (FDR) correction. All AOB and VGNG ERP scores pass the poolability test with a success rate of 99% and 100%, respectively. This is an acceptable percentage of failures, given the large amount of scores tested, allowing for a reliable division of the entire dataset into age groups.

The Bland-Altman analysis of the Test-Retest database provides test-retest reliability statistical estimates, for all combinations of tasks, conditions and parameters. These test-retest reliability results can be used by clinicians to estimate changes in BNA™ Scores between successive visits.

CONCLUSION 8.

Based on the detailed comparison to the predicate devices, the performance testing, and the clinical testing, the BNA™ Platform can be found substantially equivalent to the predicate devices.

Regulation Number and Section

§ 882.1400 Electroencephalograph.

(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).